© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149421
    Prev
    Next
    INDEX
    Explanations

    confirmation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     privilege
    -0.27
    éķij
    -0.27
    è´´
    -0.26
    orra
    -0.25
    夹
    -0.25
    Ob
    -0.25
    /bg
    -0.25
    Forg
    -0.24
     equ
    -0.24
     Bracket
    -0.24
    POSITIVE LOGITS
     confirmation
    0.44
    confirmation
    0.42
     Confirmation
    0.41
    Confirmation
    0.41
    confirm
    0.39
    .confirm
    0.39
    _confirmation
    0.38
     confirmed
    0.36
    确认
    0.36
     confirm
    0.34
    Activations Density 0.014%

    No Known Activations